mirror of
https://github.com/JarodMica/ai-voice-cloning.git
synced 2025-06-07 06:05:52 -04:00
No description
| bin | ||
| config | ||
| models | ||
| modules | ||
| src | ||
| training | ||
| voices | ||
| .dockerignore | ||
| .gitignore | ||
| .gitmodules | ||
| changelog.md | ||
| deepspeed-0.8.3+6eca037c-cp39-cp39-win_amd64.whl | ||
| Dockerfile | ||
| LICENSE | ||
| notebook_colab.ipynb | ||
| notebook_paperspace.ipynb | ||
| README.md | ||
| requirements.txt | ||
| setup-cuda-bnb.bat | ||
| setup-cuda.bat | ||
| setup-cuda.sh | ||
| setup-directml.bat | ||
| setup-docker.sh | ||
| setup-rocm-bnb.sh | ||
| setup-rocm.sh | ||
| start-docker.sh | ||
| start.bat | ||
| start.sh | ||
| train-docker.sh | ||
| train.bat | ||
| train.sh | ||
| update-force.bat | ||
| update-force.sh | ||
| update.bat | ||
| update.sh | ||
AI Voice Cloning
Note
I do not plan on actively working on improvements/enhancements for this project, this is mainly meant to keep the repo in a working state in the case the original git.ecker goes down or necessary package changes need to be made.
This repo is a fork/reupload of the one originally located here: https://git.ecker.tech/mrq/ai-voice-cloning. All of the work that was put into it to incoporate training with DLAS and inference with Tortoise belong to mrq, the author of the original ai-voice-cloning repo.
Setup
TBD
Documentation
TBD
Bug Reporting
If you run into any problems, please open up a new issue on the issues tab.